CN105472618A

CN105472618A - Pseudo base station message identification method and pseudo base station message identification device

Info

Publication number: CN105472618A
Application number: CN201410225583.8A
Authority: CN
Inventors: 吕洪赫; 任斌
Original assignee: Beijing Sogou Technology Development Co Ltd
Current assignee: Beijing Sogou Technology Development Co Ltd
Priority date: 2014-05-26
Filing date: 2014-05-26
Publication date: 2016-04-06
Anticipated expiration: 2034-05-26
Also published as: CN105472618B

Abstract

The invention discloses a pseudo base station message identification method and a pseudo base station message identification device, wherein the pseudo base station message identification method comprises the steps of receiving a message which is uploaded by a client, wherein the message comprises a client-affiliated area, message content or a message content operation value; according to the message content contained in the messages which are uploaded by at least two clients of a same affiliated area in a same time period or the operation value of the message content, determining whether the message is a pseudo base station message and obtaining a pseudo base station determining result, wherein if message content similarity in the messages uploaded by at least two clients of the same affiliated area in the same time period reaches a preset range and furthermore the message content comprises one or more rubbish message key words, determining a fact that the message is the pseudo base station message; and if the message content operation values in the messages which are uploaded by at least two clients of the same affiliated area in the same time period are same, preliminarily determining a fact that the message is the pseudo base station message. The pseudo base station message identification method and the pseudo base station message identification device realizes accurate identification for the pseudo base station message.

Description

Pseudo base station message identification method and device

Technical Field

The invention relates to the technical field of communication, in particular to a pseudo base station message identification method and a pseudo base station message identification device.

Background

The traditional sending of the spam short messages depends on an operator network, and a sending party cannot forge a sending number, so that the sending party can be quickly tracked to know who sends the spam short messages, and the sending of the spam short messages is intercepted.

The conventional spam intercepting technology can comprehensively judge the spam through the number of the sender of the short message and the content of the short message, for example, according to the fact that the content of the short message contains specific spam keywords, such as winning fraud information, the short message can be judged to be spam. Or, the determination is performed according to the number of the short message sender, for example, some specific numbers are sold to the short message sender by an operator, and the spammer of the spam short message can only use the number segment to perform spam short message sending, so that the client can directly determine the spam short message as long as the short message is sent by the number.

According to the accumulation of years, the traditional spam message interception method is stable and mature, so that the user is successfully far away from harassment, and the user is effectively prevented from being cheated. However, due to the appearance of the pseudo base station, a new challenge is brought to interception of spam messages.

The pseudo base station, i.e. pseudo base station, is a high-tech instrument, generally comprising a host and a notebook computer, and can search the mobile card information within a certain radius range by using the short message mass sender, short message sender and other related devices, and can forcibly send the short messages of fraud, advertising promotion and the like to the mobile phone of the user by arbitrarily pretending the mobile phone number of other people through the base station of the operator.

As can be seen from the above description, the sending of spam short messages by the pseudo base station has been separated from the existing operator network, and the operator cannot control the sending of spam short messages from the source any more, and furthermore, the criminal sending short messages cannot be found in the process of back check, so that the conventional spam short message interception technology is not enough to protect the information security of users, so that the users are far away from fraud and harassment, and a new method needs to be invented to determine and intercept the pseudo base station short messages.

Disclosure of Invention

The invention aims to overcome the technical problems of the existing spam short message interception technology and provide a method and a device for identifying a pseudo base station message, and the technical problems to be solved are that: and the pseudo base station information is accurately identified, and the accurate identification of the junk information is realized.

The object of the present invention and the solution to the problem can be achieved by the following technical means.

According to a first aspect of the present invention, there is provided a pseudo base station message identification method, wherein the method comprises:

receiving a message uploaded by a client, wherein the message comprises the following information: the region to which the client belongs, and the message content or the message content operation value;

judging whether the message is a pseudo base station message according to message contents or operation values of the message contents contained in messages uploaded by at least two clients in the same region to which the message belongs in the same time period to obtain a pseudo base station message judgment result, wherein,

if the similarity of message contents in messages uploaded by at least two clients in the same region in the same time period reaches a set range and the message contents contain spam keywords, determining that the messages are pseudo base station messages; or

And if the operation values of the message contents in the messages uploaded by at least two clients in the same region in the same time period are the same, preliminarily determining that the messages are pseudo base station messages.

According to a second aspect of the present invention, there is provided a pseudo base station message identification apparatus, wherein the apparatus comprises:

the message receiving unit is used for receiving messages uploaded by the client, and the messages comprise the following information: the region to which the client belongs, and the message content or the operation value of the message content;

the pseudo base station message judgment unit is used for judging whether the message is a pseudo base station message or not according to message contents or operation values of the message contents contained in messages uploaded by at least two clients in the same region to which the pseudo base station message belongs in the same time period to obtain a pseudo base station message judgment result; wherein,

According to a third aspect of the present invention, there is provided a pseudo base station message identification method, including:

receiving a message sent by a base station;

uploading the message to a cloud server, wherein the uploaded message comprises the following information: the region to which the client belongs, and the message content or the operation value of the message content;

receiving a judgment result of whether the message returned by the cloud server is a pseudo base station message or not, and carrying out corresponding processing on the message according to the judgment result;

the cloud server judges whether the message is a pseudo base station message according to message contents or operation values of the message contents contained in messages uploaded by at least two clients in the same region in the same time period; wherein,

According to a fourth aspect of the present invention, there is provided a pseudo base station message identification apparatus, comprising:

a first receiving unit, configured to receive a message sent by a base station;

the message uploading unit is used for uploading the message to a cloud server, and the uploaded message comprises the following information: the region to which the client belongs, and the message content or the operation value of the message content;

the second receiving unit is used for receiving a judgment result of whether the message returned by the cloud server is a pseudo base station message or not and carrying out corresponding processing on the message according to the judgment result;

According to a fifth aspect of the present invention, there is provided a pseudo base station message identification method, comprising:

receiving a message sent by a base station;

calculating the message weight according to at least one pseudo base station message identification rule;

if the weight or the sum of the weights of the messages reaches a set threshold value, determining the messages as pseudo base station messages;

wherein the pseudo base station message identification rule at least comprises: uploading the message to a cloud server, wherein the uploaded message comprises the following information: the method comprises the steps that the client belongs to the area and the message content or the operation value of the message content, the cloud server judges that the operation values of the message content in the messages uploaded by at least two clients in the same area in the same time period are the same, the message weight is a first set value, and otherwise, the message weight is 0; or the similarity of the message contents in the messages uploaded by at least two clients in the same region in the same time period reaches a set range, and the message contents contain spam keywords, the message weight is a second set value, otherwise, the message weight is 0.

According to a sixth aspect of the present invention, there is provided a pseudo base station message identification apparatus, comprising:

a message receiving unit, configured to receive a message sent by a base station;

the calculating unit is used for calculating the message weight according to at least one pseudo base station message identification rule;

the judging unit is used for judging whether the weight or the sum of the weights of the messages reaches a set threshold value, and if the weight or the sum of the weights of the messages reaches the set threshold value, the messages are determined to be pseudo base station messages;

By the technical scheme, the pseudo base station message identification method and the pseudo base station message identification device provided by the invention at least have the following advantages and beneficial effects:

in the embodiment, the message received by the terminal is uploaded to the cloud server, and the cloud server performs unified judgment on the message reported by the client in the same area in the same time period according to the characteristic that the pseudo base station sends the message (the users in the same area are sent in batch in the same time period), so that the capability of the pseudo base station of randomly forging numbers is effectively avoided. Meanwhile, based on the judgment of the cloud large data volume, the one-sidedness of the client based on the judgment of a single short message is avoided, and the method has higher reliability and operation flexibility, so that the accurate identification of the pseudo base station message is realized.

The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical means of the present invention more clearly understood, the present invention may be implemented in accordance with the content of the description, and in order to make the above and other objects, features, and advantages of the present invention more apparent, the following specific preferred embodiments are described in detail.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

Fig. 1 is a flowchart of a pseudo base station message identification method according to an embodiment of the present invention;

fig. 2 is a flowchart of a pseudo base station message identification method according to a second embodiment of the present invention;

fig. 3 is a flowchart of a pseudo base station message identification method according to a third embodiment of the present invention;

fig. 4 is a schematic structural diagram of a pseudo base station message identification apparatus according to a fourth embodiment of the present invention;

fig. 5 is a schematic structural diagram of a pseudo base station message identification apparatus according to a fifth embodiment of the present invention;

fig. 6 is a schematic structural diagram of a pseudo base station message identification apparatus according to a sixth embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the embodiments described in the specification are only some embodiments of the present invention, and not all embodiments. Other embodiments, which can be derived from the embodiments of the present invention by a person of ordinary skill in the art without inventive effort, are within the scope of the present invention.

Embodiment one, pseudo base station message identification method. The flow of the pseudo base station message identification method is shown in fig. 1.

In fig. 1, S100, receiving a message uploaded by a client;

the message described in this embodiment includes: mobile network based information (e.g., short messages) and/or internet based network messages.

The steps described in this embodiment may be completed by the cloud server.

The message uploaded by the client at least comprises the following information: the region to which the client belongs and the message content; or include the region to which the client belongs and the computed value of the message content. The message uploaded by the client optionally comprises a message sender number and a client network state, wherein the client network state comprises a network state when the client uploads the message and a network state when the client receives the message. The message uploaded by the client optionally also comprises the message receiving time of the client.

The region to which the client belongs, that is, the region to which the client belongs when receiving the message, may be a specific longitude and latitude of a location where the client receives the message, or a block, a house number, or the like of the location where the client receives the message. The technical embodiment for obtaining the area of the client is not specifically limited.

The range of the same region as that described in this embodiment and the following embodiments is greater than or equal to the range that can be covered by one base station. For example, the coverage area of the base station is 3 km, and the coverage area of the same region in this embodiment may be set to 3.5 km.

The operation value of the message content in this embodiment and the following embodiments is a value obtained by performing operations such as encryption on the message content, for example, a value obtained by performing MD5 operations on the message content.

In this embodiment, the message received by the client may be uploaded to the cloud server before being displayed to the user, and the cloud server identifies whether the message is a pseudo base station message. It should be noted that the cloud server does not affect the identification and interception processing operations of the existing spam messages while identifying the pseudo base station messages, that is, the client can upload all received messages to the cloud server, and also can identify whether the messages are spam messages or not, if the spam messages can be determined, the messages are directly intercepted and not uploaded to the cloud server, and in short, the client uploads the messages to the cloud server under the condition that whether the messages are pseudo base station messages or not needs to be confirmed.

It should be noted that, because the client is connected to the pseudo base station and cannot connect to the normal network instantly, the client cannot upload the message to the cloud server, the client in this embodiment may detect the network connection state of the client in real time, and when the client is disconnected from the pseudo base station and connected to the operator network or WiFi, the client immediately uploads the message to the cloud server. In addition, the client can upload the message to the cloud server through the WiFi.

S110, judging whether the message is a pseudo base station message or not according to message contents or operation values of the message contents contained in messages uploaded by at least two clients in the same region in the same time period to obtain a pseudo base station message judgment result;

the dividing manner of the same time period in this embodiment and the following embodiments may include the following two cases:

1) the message uploaded by the client further comprises a message receiving time of the client, and the same time period is divided according to the message receiving time of the client; or

2) And the same time period is divided according to the time for receiving the message uploaded by the client, namely the time period divided by the time for receiving the message uploaded by the client by the cloud server.

Aiming at the mass sending property of the message sent by the pseudo base station, namely the pseudo base station generally sends the message to users in one area in batches, and the users in the same area can receive the same message in the same time period. Therefore, when the pseudo base station message is identified, the embodiment of the invention judges the messages uploaded by at least two clients in the same region in the same time period. The time duration of the same time period in this embodiment may be set according to needs, and considering that there is a time difference between receiving a message and uploading a message by different clients, the time duration setting is not too short, and may be set to, for example, 5 minutes, 10 minutes, 20 minutes, and the like, but is not limited thereto.

In order to protect the privacy of the user, the embodiment of the present invention may upload the operation value of the message content instead of uploading the message content to the cloud server, that is, the uploaded message includes the following information: and the cloud server identifies and judges the pseudo base station message based on the region to which the client belongs and the operation value of the message content in the same time period.

S120, if the operation values of the message contents in the messages uploaded by at least two clients in the same region in the same time period are the same, preliminarily determining that the messages are pseudo base station messages.

S130, if the similarity of the message contents in the messages uploaded by at least two clients in the same region in the same time period reaches a set range and the message contents contain spam keywords, determining that the messages are pseudo base station messages.

The step is that the message uploaded based on the client comprises the following information: the region to which the client belongs and the judgment of the message content execution.

In this embodiment, under the condition that the similarity of the message contents in the messages uploaded by at least two clients in the same region in the same time period is determined to reach the set range, whether the message contents include spam keywords is further identified, and if so, the message is determined to be a pseudo base station message. The method for identifying whether the content of the message contains the spam keyword is not specifically limited in this embodiment, for example, the keyword frequently contained in the spam message can be stored in a database based on a data accumulation mode, whether the content of the message contains the spam keyword can be identified according to the spam keyword recorded in the database, and the message is determined to be the pseudo base station message under the condition that the spam keyword is contained.

In this embodiment, the similarity of the message contents may be compared by using a conventional edit distance algorithm (LecenshtheinDistance).

If the cloud server determines that the similarity of the message contents in the messages uploaded by at least two clients in the same region in the same time period does not reach the set range, the embodiment may determine a single message uploaded by each client, and at this time, the method for identifying the pseudo base station message in the embodiment includes at least one or more of the following steps:

identifying whether the message uploaded by the client side meets the association or not according to the association between the pseudo base station common number and the message content, and if so, determining the message as a pseudo base station message;

and identifying whether the message uploaded by the client side accords with the content mode or not according to the common content mode of the pseudo base station, and if so, determining the message as the pseudo base station message. The association between the pseudo base station common numbers and the message contents and the pseudo base station common content mode can be obtained by the cloud server based on a large amount of data accumulation and by adopting a machine learning method, such as a naive Bayes classification algorithm.

S140, sending the judgment result of the pseudo base station message to a client;

in this embodiment, after the pseudo base station message determination result is obtained, the pseudo base station message determination result may be sent to the client. In this embodiment, the result of the pseudo base station message determination is: in case of preliminary determination as a pseudo base station message:

in one embodiment, a client is prompted to identify whether the message content contains spam keywords, and if the message content contains spam keywords, the message is determined to be a pseudo base station message; namely, the client is informed that the message identification result is: the message is determined to be a pseudo base station message preliminarily, the client can further identify according to the message content, for example, if the client identifies that the message content of the message contains a spam keyword, the message can be further determined to be a pseudo base station message.

In another embodiment, the client is notified to upload the message content, whether the message content uploaded by the client contains spam keywords is identified, and if yes, the message is further determined to be a pseudo base station message. Namely, the client is informed that the message identification result is: the preliminary determination is a pseudo base station message. If the message content needs to be further identified, the message content needs to be uploaded to a cloud server, the cloud server identifies whether the message content contains spam keywords, if the message content contains the spam keywords, the message can be further determined to be a pseudo base station message, and if the message content does not contain the spam keywords, the message is a non-pseudo base station message.

In this embodiment, the result of the pseudo base station message determination is: and under the condition that the message is determined to be the pseudo base station message, the client can be informed that the message is the pseudo base station message, and the client can be prompted to intercept the message. The interception processing described in this embodiment is to prompt the user about the amount of intercepted messages and other information without directly displaying the message content to the user, and the user displays the message content to the user when selecting to view.

Meanwhile, the embodiment can store preliminarily determined pseudo base station messages and information contained in the determined pseudo base station messages in a database as a material for cloud server statistical analysis and machine learning, and the information of the messages to be stored includes but is not limited to: the region to which the client belongs, the message content or the message content operation value. The information of the message to be saved may further include: the client receives the message time or the cloud server receives the time of the client uploading the message, and optionally further comprises a client network state and a message sender number, wherein the client network state comprises a network state when the client uploads the message and a network state when the client receives the message.

The embodiment uniformly judges the messages reported by the client sides in the same area in the same time period according to the characteristic that the pseudo base station sends the messages (the users in the same area are sent in batch in the same time period), thereby effectively avoiding the capability of the pseudo base station to forge any number randomly. Meanwhile, the one-sidedness of single short message judgment is avoided based on the judgment of the cloud large data volume, and the method has higher reliability and operation flexibility.

In the second embodiment, a pseudo base station message identification method, a flowchart of the pseudo base station message identification method refers to fig. 2, and specifically includes the following operations.

S200, receiving a message sent by a base station;

S210, uploading the message to a cloud server;

the message uploaded by the client at least comprises the following information: the region to which the client belongs and the message content; or include the region to which the client belongs and the computed value of the message content. The message uploaded in this embodiment optionally includes a message sender number and a client network state, where the client network state includes a network state when the client uploads the message and a network state when the client receives the message. The message uploaded in this embodiment optionally includes a message receiving time of the client.

The calculated value of the message content is a value obtained by performing an operation such as encryption on the message content, for example, a value obtained by performing an operation of MD5 on the message content. In one embodiment of the present invention, in order to protect the privacy of the user, it may be considered that the message content is not uploaded to the cloud server, but the operation value of the message content is uploaded, that is, the uploaded message includes the following information: and the cloud server identifies and judges the pseudo base station message based on the region to which the client belongs and the operation value of the message content in the same time period.

In this embodiment, the message received by the client may be uploaded to the cloud server before being displayed to the user, and the cloud server identifies whether the message is a pseudo base station message.

It should be noted that the client may upload all received messages to the cloud server, or may first identify whether the received messages are spam messages, and if the received messages are spam messages, the messages are directly intercepted and not uploaded to the cloud server, that is, the client may upload the messages to the cloud server only when it is necessary to determine whether the messages are pseudo base station messages.

In addition, because the client is connected with the pseudo base station and cannot be connected with a normal network instantly, the message cannot be uploaded to the cloud server, the client can detect the network connection state of the client in real time, and the message can be immediately uploaded to the cloud server after the client is disconnected from the pseudo base station and connected with an operator network or connected with WiFi. The client can upload the message to the cloud server through the WiFi.

S220, receiving a judgment result of whether the message returned by the cloud server is a pseudo base station message or not, and carrying out corresponding processing on the message according to the judgment result;

aiming at the mass sending property of the message sent by the pseudo base station, namely the pseudo base station generally sends the message to users in one area in batches, and the users in the same area can receive the same message in the same time period. Therefore, in an embodiment of the present invention, when identifying the pseudo base station message, the cloud server determines a message uploaded by at least two clients in the same region in the same time period, where the pseudo base station message belongs to the same region, and specifically, the method for identifying the pseudo base station message includes:

1) if the similarity of message contents in messages uploaded by at least two clients in the same region in the same time period reaches a set range and the message contents contain spam keywords, determining that the messages are pseudo base station messages; the cloud server of this embodiment may compare the similarity of the message contents by using a conventional edit distance algorithm (LecenshtheinDistance).

In this embodiment, under the condition that the similarity of the message contents in the messages uploaded by at least two clients in the same region in the same time period is determined to reach the set range, whether the message contents include spam keywords is further identified, and if so, the message is determined to be a pseudo base station message. The method for identifying whether the content of the message contains the spam keyword is not particularly limited in this embodiment, for example, the keyword frequently contained in the spam message can be stored in a database based on a data accumulation mode, whether the content of the message contains the spam keyword can be identified according to the spam keyword recorded in the database, and the message is determined to be the pseudo base station message under the condition that the spam keyword is contained.

This is based on the fact that the message uploaded by the client includes the following information: the region to which the client belongs and the judgment of the message content execution.

2) And if the operation values of the message contents in the messages uploaded by at least two clients in the same region in the same time period are the same, preliminarily determining that the messages are pseudo base station messages.

If the cloud server determines that the message content similarity in the messages uploaded by at least two clients in the same region in the same time period does not reach the set range, the cloud server in this embodiment may determine the pseudo base station message for a single message uploaded by each client, where the determination method includes, but is not limited to, at least one or more of the following:

and identifying whether the message uploaded by the client side accords with the content mode or not according to the common content mode of the pseudo base station, and if so, determining the message as the pseudo base station message.

The association between the pseudo base station common number and the message content can be obtained by the cloud server based on a large amount of data accumulation and by adopting a machine learning method, such as a naive Bayesian classification algorithm. Similarly, the pseudo base station common content mode is obtained by the cloud server based on a large amount of data accumulation and by adopting a machine learning method.

Wherein, this embodiment cloud server can deposit the information of pseudo base station message of confirmed and preliminary definite pseudo base station message in the database, and as the material of cloud server statistical analysis and machine learning, wherein the information that needs to be preserved includes but not limited to: the region to which the client belongs, the message content or the message content operation value. The method can also comprise the following steps: the client receives the message time or the cloud server receives the time of the client uploading the message, in addition, the information required to be stored optionally comprises a client network state and a message sender number, and the client network state comprises a network state when the client uploads the message and a network state when the client receives the message.

In this embodiment, the performing the corresponding processing on the message according to the determination result includes, but is not limited to, at least one of the following situations:

in one case, if the judgment result is that the cloud server determines that the message is a pseudo base station message, the pseudo base station message is intercepted. The interception processing described in this embodiment is not to directly display the message content to the user, but certainly may prompt the user about the information such as the number of intercepted messages, and the message content is displayed to the user when the user selects to view the message content.

In another case, if the determination result is that the cloud server preliminarily determines that the message is a pseudo base station message, the processing method includes, but is not limited to, at least one of the following:

in one embodiment, identifying whether the message content preliminarily determined to be the pseudo base station message contains a spam keyword, and if so, further determining that the message is the pseudo base station message; or

In another embodiment, the message content is uploaded to a cloud server, and a further judgment result returned by the cloud server according to the message content is received, wherein the cloud server judges that the message content contains spam keywords, and then the message is further determined to be a pseudo base station message.

In the embodiment, the client uploads the message to the cloud server, and the cloud server performs unified judgment on the message reported by the client in the same area in the same time period according to the characteristic that the pseudo base station sends the message (the users in the same area are sent in batch in the same time period), so that the capability of the pseudo base station of randomly forging numbers is effectively avoided. Meanwhile, the judgment based on the cloud large data volume avoids the one-sidedness of the client based on the judgment of a single short message, and the method has higher reliability and operation flexibility.

In the third embodiment, a pseudo base station message identification method, a flowchart of the pseudo base station message identification method refers to fig. 3, and specifically includes the following operations.

S300, receiving a message sent by a base station;

S310, calculating the message weight according to at least one pseudo base station message identification rule;

the pseudo base station message identification rule in the embodiment of the invention at least comprises one or more of the following methods:

1) uploading the message to a cloud server, and receiving the message weight calculated and returned by the cloud server, wherein the message uploaded by the client at least comprises the following information: the region to which the client belongs and the message content; or include the region to which the client belongs and the computed value of the message content. The cloud server judges that the operation values of message contents in messages uploaded by at least two clients in the same region in the same time period are the same, the message weight is a first set value, and if the message weights are different, the message weights are 0; or judging that the similarity of the message contents in the messages uploaded by at least two clients in the same region in the same time period reaches a set range and contains spam keywords, wherein the message weight is a second set value, and otherwise, the message weight is 0.

The specific method for the cloud server to identify the pseudo base station message is as described in the first embodiment, and is not described herein again.

It should be noted that, in the first embodiment, when the cloud server preliminarily determines that the message is a pseudo base station message according to the region to which the client belongs and the operation value of the message content, the message weight is a first set value, otherwise, the message weight is 0;

and when the cloud server determines that the message is the pseudo base station message according to the region and the message content of the client, the message weight is a second set value, otherwise, the message weight is 0.

The at least one pseudo base station message identification rule according to this embodiment further includes, but is not limited to, at least one or more of the following methods:

and 2) when the message is received, if the network is in an abnormal state, detecting the network connectivity, if the network is connected, the message weight is 0, and if the network is interrupted, the message weight is a third set value.

In this embodiment, the network being in an abnormal state includes: networking state after a network momentary interruption. The client in this embodiment can detect the network connection state in real time, and if the network is connected after being interrupted instantaneously (for example, for 8 to 12 seconds), it indicates that the network is in an abnormal state.

The method comprises the steps that a pseudo base station can cause instantaneous interruption of a terminal network when being connected with a terminal, so that the network is abnormal, after interruption, a message received at the moment of connection is possibly a pseudo base station message received under the condition of connection with the pseudo base station, at the moment, the terminal is not connected with a normal operator network, namely, the terminal network is still in an interruption state, therefore, the connectivity of the network is detected when the message is received under the networking state after the instantaneous interruption of the network, if the network is connected, the received message is a message sent through the normal operator network, and if the network is not connected, the message weight is determined to be 0; if the network is interrupted, the received message is the message sent by the pseudo base station, but not the message sent by the operator network, and the message weight is determined to be a third set value.

The method for detecting network connectivity provided by this embodiment includes, but is not limited to: and sending a message to a number provided by an operator in advance, if the sending is successful, determining that the network is connected, and if the sending is failed, determining that the network is interrupted.

The method 3) extracts the appointed additional information in the message, judges whether the additional information is a specified value, if the additional information is the specified value, the message weight is 0, and if the additional information is not the specified value, the message weight is a fourth set value.

In this embodiment, the specifying the additional information in the extraction message includes: an SMSC (Mobile center number) extracting a message, and determining whether the extracted SMSC is consistent with a local SMSC.

Since the number of SMSC of each region is unique, the forged SMSC is not matched with the SMSC of the local region when the pseudo base station sends the message, so that whether the received message is the pseudo base station message can be judged by the SMSC. Comparing the extracted SMSC with the local SMSC, if the extracted SMSC is consistent with the local SMSC, determining that the message weight is 0, and if the extracted SMSC is not consistent with the local SMSC, determining that the message weight is a fourth set value.

Method 4) judges whether the base station information is matched with the base station information of the current position, if so, the message weight is 0, and if not, the message weight is a fifth set value.

In this embodiment, the base station information includes a base station ID, and whether the base station ID matches the base station ID of the current location is determined.

Because the number of the base stations is large, the base station ID can be forged when the pseudo base station sends the message, but the base station ID is not necessarily matched with the base station ID of the current position of the user, so that the base station ID of the message is extracted, and whether the message is the pseudo base station message can be judged by comparing the extracted base station ID with the base station ID of the current position, namely, if the extracted base station ID is consistent with the base station ID of the current position, the message weight is 0, and if the extracted base station ID is not consistent with the base station ID of the current position, the message weight is a fifth set value.

Method 5) according to the message content and the sender number, judging whether the message content is a junk message with a correct number recorded in a database or judging whether the sender number is a junk number, if not, the message weight is 0, and if so, the message weight is a sixth set value. For example, some fraud short messages pretend to be bank numbers, the sender numbers displayed by the fraud short messages are bank numbers recorded in a database, such as 95555, but the fraud short messages are actually sent by a pseudo base station rather than a bank; and for example, some fraud flights need to change their signs, which are actually not the short messages sent by the airline company, but the sender number is displayed and is the airline company.

The method may be similar to the existing method for identifying spam messages, and is not specifically limited herein, and when the identification result is a spam message with a correct number recorded in the database, or the sender number is a spam number, the message weight is a sixth setting value, otherwise, the message weight is 0.

S320, judging whether the weight or the sum of the weights of the messages reaches a set threshold value;

and if the weight or the sum of the weights of the messages reaches a set threshold value, the step S330 is carried out, and the messages are determined to be pseudo base station messages.

After receiving a message sent by a base station, a terminal can simultaneously adopt the five methods to respectively calculate the weight value of the message, and if the weight value calculated by any method reaches a set threshold value, the message is determined to be a pseudo base station message; or the sum of the weights calculated by any two or more methods reaches a set threshold value, and the message is determined to be a pseudo base station message. It can be understood that, the weight values of the messages are calculated by the above five methods at the same time, and it is not limited that the execution time of each method is completely consistent, but rather, the determination may be performed by a plurality of methods in the process of identifying and determining the pseudo base station message.

In addition, the invention also provides an embodiment, any one or more of methods 2) to 5) can be adopted to calculate the message weight locally at the terminal, if the sum of the calculated message weights is less than a set threshold value, the message is uploaded to the cloud server, the cloud server continues to calculate the message weight by adopting the method 1), and then whether the message weight calculated by the cloud server reaches the set threshold value is judged, and if the message weight reaches the set threshold value, the message is determined to be a pseudo base station message; and if the sum of the weights of all the calculated messages reaches the set threshold, calculating whether the sum of the weights of all the calculated messages reaches the set threshold.

In the process of calculating the weights by the above-mentioned methods, if the sum of the weight values calculated by any one method or the sum of the weight values calculated by the multiple methods reaches a set threshold, it may be determined that the message is a pseudo base station message, and the calculation by other methods may be stopped.

If the sum of the message weights does not reach the set threshold, step S340 is entered to determine that the message is not a pseudo base station message.

Because the pseudo base station message is determined to have inaccurate condition by adopting a single method, the pseudo base station message is identified by adopting a plurality of methods in a combined way, the problem of misjudgment caused by the fact that the pseudo base station message is identified by the single method is solved, and the accuracy of identifying the pseudo base station message is greatly improved.

In the fourth embodiment, the pseudo base station message identification device may be in the same physical entity as the cloud server. The method for the apparatus to specifically identify the pseudo base station message may correspond to an embodiment.

The schematic structural diagram of the pseudo base station message identification apparatus is shown in fig. 4, and the apparatus mainly includes: message receiving section 400, pseudo base station message determining section 410, and transmitting section 420. The method can further comprise the following steps: a holding unit 430.

The message receiving unit 400 in this embodiment is mainly configured to receive a message uploaded by a client, where the message includes the following information: the region to which the client belongs and the message content, or the operation value of the region to which the client belongs and the message content. Optionally, the network status of the client includes a network status when the client uploads the message and a network status when the client receives the message. The message uploaded by the client optionally comprises the message receiving time of the client.

The message described in this embodiment includes: mobile network based information (e.g., sms)/or internet based network messages.

In addition, because the client is connected with the pseudo base station and cannot be connected with a normal network instantly, the message cannot be uploaded to the cloud server, the client network connection state can be detected in real time, and the message can be immediately uploaded to the cloud server after the client is disconnected from the pseudo base station and connected with an operator network or connected with WiFi. The client can upload the message to the cloud server through the WiFi.

The pseudo base station message determining unit 410 in this embodiment is mainly configured to determine whether a message is a pseudo base station message according to message contents or operation values of the message contents included in messages uploaded by at least two clients in the same region to which the message belongs in the same time period;

aiming at the mass sending property of the message sent by the pseudo base station, namely the pseudo base station generally sends the message to users in one area in batches, and the users in the same area can receive the same message in the same time period. Therefore, in the embodiment of the invention, when the pseudo base station message is identified, the message uploaded by at least two clients in the same region is judged in the same time period.

In order to protect the privacy of the user, an embodiment of the present invention may upload the operation value of the message content instead of uploading the message content to the cloud server, that is, the uploaded message includes the following information: and the cloud server identifies and judges the pseudo base station message based on the region to which the client belongs and the operation value of the message content.

In one embodiment, if the similarity of the message contents in the messages uploaded by at least two clients in the same region in the same time period reaches a set range and the message contents include spam keywords, the pseudo base station message determining unit 510 determines that the messages are pseudo base station messages; wherein the proximity of the message content may be calculated using conventional edit distance algorithms.

In another embodiment, if the computation values of the message contents in the messages uploaded by at least two clients in the same region in the same time period are the same, the pseudo base station message determining unit 410 preliminarily determines that the messages are pseudo base station messages.

In another embodiment, if the pseudo base station message determining unit 410 determines that the message content similarity in the messages uploaded by at least two clients in the same region in the same time period does not reach the set range, the pseudo base station message determining unit 410 further includes at least one of the following sub-units:

a first determining subunit 4110 (not shown in the figure), configured to identify, when it is determined that similarity between message contents in messages uploaded by at least two clients in the same region in the same time period does not reach the set range, whether the message uploaded by the client conforms to the association according to the association between the common pseudo base station number and the message content when the message received by the message receiving unit 400 includes a message sender number, and if so, determine that the message is a pseudo base station message;

a second determining subunit 4120 (not shown in the figure), configured to, when it is determined that similarity between message contents in messages uploaded by at least two clients in the same region in the same time period does not reach the set range, identify whether the message uploaded by the client conforms to the content pattern, and if so, determine that the message is a pseudo base station message.

The sending unit 420 is configured to send the pseudo base station message determination result to the client.

The storing unit 430 in this embodiment is configured to store information included in the determined pseudo base station message or the preliminarily determined pseudo base station message. The information to be saved is the same as that described in the first embodiment, and is not described herein again.

The apparatus according to an embodiment of the present invention may further include:

a first prompting unit 440 (not shown in the figure), configured to prompt the client to identify whether a message content includes a spam keyword or not when the pseudo base station message determining unit preliminarily determines that the message is a pseudo base station message, and if the message includes the spam keyword, determine that the message is a pseudo base station message;

a notification and receiving unit 450 (not shown in the figure) for notifying the client to upload the message content, receiving the message content uploaded by the client and transmitting the message content to the pseudo base station message determining unit;

at this time, the pseudo base station message determining unit 410 is further configured to identify whether a message content uploaded by the client includes a spam keyword, and if the message content includes the spam keyword, further determine that the message is a pseudo base station message.

The device according to another embodiment of the present invention may further include:

a second prompting unit 460 (not shown in the figure), configured to prompt the client to perform an interception process on the pseudo base station message when the pseudo base station message determining unit 410 determines that the message is a pseudo base station message.

Fifth, the pseudo base station message identification apparatus in this embodiment may be located in the same physical entity as a client, where the client includes but is not limited to a mobile smart client or a PC. The method for the apparatus to specifically identify the pseudo base station message may correspond to the embodiments.

As shown in fig. 5, the structure of the device is schematically illustrated, and the device mainly includes: a first receiving unit 500, a message uploading unit 510 and a second receiving unit 520. An identification unit 530 and an interception unit 540 are also optionally included.

The first receiving unit 500 in this embodiment is mainly configured to receive a message sent by a base station; the message described in this embodiment includes: mobile network based information (e.g., short messages) and/or internet based network messages.

A message uploading unit 510, configured to upload the message to a cloud server, where the uploaded message at least includes the following information: the region to which the client belongs and the message content; or include the region to which the client belongs and the computed value of the message content. The uploaded message optionally contains a message sender number and a client network state, and the client network state comprises a network state when the client uploads the message and a network state when the client receives the message. The message uploaded by the client optionally also comprises the message receiving time of the client.

It should be noted that, in this embodiment, all received messages may be uploaded to the cloud server, or whether the received messages are spam messages may be identified first, and if the received messages are spam messages, the messages are directly intercepted and not uploaded to the cloud server, that is, only when it is necessary to confirm whether the messages are pseudo base station messages, the messages are uploaded to the cloud server.

In addition, since the client is connected to the pseudo base station and cannot be connected to the normal network instantly, the client cannot upload the message to the cloud server, the client in this embodiment may detect the network connection state in real time, and when the client is disconnected from the pseudo base station and connected to the operator network or connected to the WiFi, the message uploading unit 510 may upload the message to the cloud server immediately through the WiFi.

In this embodiment, the second receiving unit 520 is mainly configured to receive a determination result of whether the message returned by the cloud server is a pseudo base station message, and perform corresponding processing on the message according to the determination result;

if the similarity of message contents in messages uploaded by at least two clients in the same region in the same time period reaches a set range and the message contents contain spam keywords, determining that the messages are pseudo base station messages; the cloud server may calculate the proximity of the message content using a conventional edit distance algorithm. Or

The specific method for identifying the pseudo base station message by the cloud server in this embodiment is the same as that in the first embodiment, and details are not repeated here.

The method for the second receiving unit 520 to perform corresponding processing on the message according to the determination result includes, but is not limited to:

in an embodiment, when the second receiving unit 520 receives the message that the cloud server preliminarily determines that the message is the pseudo base station message, the message uploading unit 510 is further configured to upload the message content to the cloud server, and the second receiving unit 520 is further configured to receive a further determination result according to the message content returned by the cloud server, where the cloud server determines whether the message content includes a spam keyword, and if so, further determines that the message is the pseudo base station message.

In another embodiment, when the second receiving unit 520 receives the message that the cloud server preliminarily determines that the message is a pseudo base station message, the identifying unit 530 identifies whether the message content of the message includes a spam keyword, and if so, further determines that the message is a pseudo base station message. The specific identification method is the same as that described in embodiment two, and is not described herein again.

The intercepting unit 540 according to this embodiment is configured to perform intercepting processing on the determined pseudo base station message. The interception processing described in this embodiment is to prompt the user about the amount of intercepted messages and other information without directly displaying the message content to the user, and the user displays the message content to the user when selecting to view.

The pseudo base station message identification device uploads the received message to the cloud server, and the cloud server uniformly judges the message reported by the client in the same area in the same time period according to the characteristic that the pseudo base station sends the message (the users in the same area are sent in batch in the same time period), so that the capability of the pseudo base station to forge any number is effectively avoided. Meanwhile, the judgment based on the cloud large data volume avoids the one-sidedness of the client based on the judgment of a single short message, and the method has higher reliability and operation flexibility.

In a sixth embodiment, the pseudo base station message identification apparatus may be located in the same physical entity as a client, where the client includes but is not limited to a mobile smart client or a PC. The method for the apparatus to specifically identify the pseudo base station message may correspond to the third embodiment.

As shown in fig. 6, which is a schematic structural diagram of the apparatus, the apparatus mainly includes: message receiving section 600, calculating section 610, and determining section 620.

The message receiving unit 600 is mainly configured to receive a message sent by a base station;

The calculating unit 610 in this embodiment is mainly configured to calculate the message weight according to at least one pseudo base station message identification rule;

the various pseudo base station message identification rules in this embodiment are the same as those in embodiment three, and are not described herein again.

A determining unit 620, configured to determine whether the message weight or the sum of the message weights reaches a set threshold, and if the message weight or the sum of the message weights reaches the set threshold, determine that the message is a pseudo base station message.

If the message weight or the sum of the weights reaches a set threshold, the determining unit 620 determines that the message is a pseudo base station message.

After receiving the message sent by the base station, the terminal can simultaneously adopt the five methods described in the third embodiment to respectively calculate the weight value of the message, and if the weight value calculated by any method reaches a set threshold value, the message is determined to be a pseudo base station message; or the sum of the weights calculated by any two or more methods reaches a set threshold value, and the message is determined to be a pseudo base station message.

If the sum of the message weights does not reach the set threshold, the determining unit 620 determines that the message is not a pseudo base station message.

In addition, the present invention further provides an embodiment, wherein the calculating unit 610 may first locally calculate the message weight by using any one or more of the methods 2) to 5) above, if the sum of the calculated message weights is less than a set threshold, then upload the message to the cloud server, and continue to calculate the message weight by using the method 1) from the cloud server, and then determine whether the message weight calculated by the cloud server reaches the set threshold through the determining unit 620, and if the message weight reaches the set threshold, determine that the message is a pseudo base station message; if the set threshold is not reached, the calculation unit calculates whether the sum of the weights of all the method calculation messages reaches the set threshold.

In summary, in this embodiment, a message received by the terminal is uploaded to the cloud server, and the cloud server performs unified determination on messages reported by clients in the same area in the same time period according to the characteristic that the pseudo base station sends the message (the users in the same area are sent in batches in the same time period), so that the capability of the pseudo base station of arbitrarily forging numbers is effectively avoided. Meanwhile, the client side is prevented from judging one sidedness based on a single short message based on the judgment of the cloud side large data volume, and the reliability is higher.

Meanwhile, the pseudo base station can change continuously, and the judgment strategy can be improved at any time according to the change of the pseudo base station based on the recognition of the pseudo base station message by the cloud server, so that the method has strong operation flexibility.

From the above description of the embodiments, it is clear to those skilled in the art that the present invention can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, embodiments of the apparatus or system are substantially similar to the method embodiments and therefore are described in a relatively simple manner, where relevant reference may be made to some descriptions of the method embodiments. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

The method and the device for identifying the pseudo base station message provided by the invention are described in detail, a specific example is applied in the text to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.

Claims

1. A pseudo base station message identification method is characterized by comprising the following steps:

2. The pseudo base station message identification method of claim 1, further comprising:

and sending the pseudo base station message judgment result to the client.

3. The pseudo base station message identification method according to claim 1, wherein if the similarity of message contents in messages uploaded by at least two clients in the same region in the same time period does not reach the set range, the method further comprises at least one of the following steps:

under the condition that the message also contains a message sender number, identifying whether the message uploaded by the client side accords with the association according to the association between the pseudo base station common number and the message content, and if the message accords with the association, determining the message as the pseudo base station message;

4. The pseudo base station message identification method according to claim 1, wherein if the message is preliminarily determined to be a pseudo base station message, the method further comprises any one of:

prompting the client to identify whether the message content contains a spam keyword, and if so, determining that the message is a pseudo base station message;

informing the client to upload message content, identifying whether the message content uploaded by the client contains spam keywords, and if so, further determining that the message is a pseudo base station message.

5. The method of claim 1, wherein if the message is determined to be a pseudo base station message, the method further comprises:

and prompting the client to intercept the pseudo base station message.

6. The pseudo base station message identification method according to claim 1, wherein after obtaining the pseudo base station message judgment result, further comprising:

and saving the information contained in the determined pseudo base station message or the preliminarily determined pseudo base station message.

7. A pseudo base station message identification apparatus, comprising:

8. The pseudo base station message identification device of claim 7, further comprising:

and the sending unit is used for sending the pseudo base station message judgment result to the client.

9. The pseudo base station message identification device of claim 7, wherein the pseudo base station message determining unit further comprises at least one of:

the first judging subunit is used for identifying whether the message uploaded by the client side meets the association according to the association between the common pseudo base station number and the message content under the condition that the similarity of the message contents in the messages uploaded by at least two client sides in the same region in the same time period is judged to not reach the set range and the message receiving unit receives the message which also contains the message sender number, and if so, determining that the message is a pseudo base station message;

and the second judging subunit is used for identifying whether the message uploaded by the client side meets the content mode or not under the condition of judging that the message content similarity in the messages uploaded by at least two client sides in the same region in the same time period does not reach the set range, and if the message content similarity meets the content mode, determining that the message is a pseudo base station message.

10. The pseudo base station message identification device of claim 7, further comprising any of:

the first prompting unit is used for prompting the client to identify whether the message content contains a spam keyword or not under the condition that the pseudo base station message judging unit preliminarily determines that the message is the pseudo base station message, and if the message contains the spam keyword, the message is determined to be the pseudo base station message;

the notification and receiving unit is used for notifying the client to upload the message content, receiving the message content uploaded by the client and transmitting the message content to the pseudo base station message judgment unit;

the pseudo base station message judging unit is further used for identifying whether the message content uploaded by the client contains spam keywords or not, and if the message content contains spam keywords, the message is further determined to be pseudo base station message.

11. The pseudo base station message identification device of claim 7, further comprising:

and the second prompting unit is used for prompting the client to intercept the pseudo base station message under the condition that the pseudo base station message judging unit determines that the message is the pseudo base station message.

12. The pseudo base station message identification device of claim 7, further comprising:

and the storage unit is used for storing the determined pseudo base station message or the information contained in the preliminarily determined pseudo base station message.

13. A pseudo base station message identification method is characterized by comprising the following steps:

receiving a message sent by a base station;

14. The pseudo base station message identification method according to claim 13, wherein if the determination result returned by the cloud server is: preliminarily determining that the message is a pseudo base station message, further comprising:

identifying whether the message content of the pseudo base station message is preliminarily determined to contain spam keywords, and further determining the message to be the pseudo base station message if the message content of the pseudo base station message contains the spam keywords; or

And uploading the message content to a cloud server, and receiving a further judgment result returned by the cloud server according to the message content, wherein the cloud server judges that the message content contains spam keywords, and further determines that the message is a pseudo base station message.

15. The method according to claim 13, wherein if the similarity of message contents in the messages uploaded by at least two clients in the same area in the same time period is not within the predetermined range, the method further comprises:

if the uploaded message also comprises a message sender number, identifying whether the message uploaded by the client side accords with the correlation according to the correlation between the pseudo base station common number and the message content, and if so, determining the message to be a pseudo base station message; or

16. The pseudo base station message identification method according to claim 13, wherein if the determination result returned by the cloud server is: determining that the message is a pseudo base station message, further comprising:

and intercepting the determined pseudo base station message.

17. A pseudo base station message identification apparatus, comprising:

a first receiving unit, configured to receive a message sent by a base station;

18. The pseudo base station message identification device of claim 17, further comprising:

the identification unit is used for identifying whether the message content of the message contains spam keywords or not under the condition that the second receiving unit receives the message and preliminarily determines that the message is the pseudo base station message, and if the message contains the spam keywords, the message is further determined to be the pseudo base station message.

19. The pseudo base station message identification device as claimed in claim 17 wherein the message uploading unit is further configured to:

when the second receiving unit receives the message which is preliminarily determined to be the pseudo base station message by the cloud server, the message content is uploaded to the cloud server;

the second receiving unit is further configured to receive a further judgment result returned by the cloud server according to the message content, where the cloud server judges whether the message content includes a spam keyword, and if so, further determines that the message is a pseudo base station message.

20. The pseudo base station message identification device of claim 17, further comprising:

and the interception unit is used for intercepting the determined pseudo base station message.

21. A pseudo base station message identification method is characterized by comprising the following steps:

receiving a message sent by a base station;

22. The pseudo base station message identification method of claim 21, wherein the pseudo base station message identification rules further comprise at least one or more of:

when the message is received, if the network is in an abnormal state, detecting the network connectivity, if the network is connected, the message weight is 0, and if the network is interrupted, the message weight is a third set value;

extracting specified additional information in the message, judging whether the additional information is a specified value, if so, the message weight is 0, and if not, the message weight is a fourth set value;

judging whether the base station information is matched with the base station information of the current position, if so, the message weight is 0, and if not, the message weight is a fifth set value;

and judging whether the message content is a junk message with a correct number recorded in a database or judging whether the sender number is a junk number according to the message content and the sender number, wherein if not, the message weight is 0, and if so, the message weight is a sixth set value.

23. The pseudo base station message identification method of claim 22, wherein said network being in an abnormal state comprises: networking state after a network momentary interruption.

24. The pseudo base station message identification method of claim 22, wherein additional information is specified in the extracted message, and wherein determining whether the additional information is a prescribed value comprises:

and extracting the mobile center number of the message, and judging whether the mobile center number is consistent with the local area mobile center number.

25. The method of claim 22, wherein the determining whether the base station information matches the current location base station information comprises:

and judging whether the base station identification ID is matched with the current position base station ID.

26. A pseudo base station message identification apparatus, comprising:

27. The pseudo base station message identification device of claim 26, wherein the pseudo base station message identification rules further comprise at least one or more of:

28. The pseudo base station message identification device of claim 27 wherein the network being in an abnormal state comprises: networking state after a network momentary interruption.

29. The pseudo base station message identification device of claim 27 wherein additional information is specified in the extracted message and determining whether the additional information is a specified value comprises:

30. The pseudo base station message identification device of claim 27, wherein the determining whether the base station information matches the current location base station information comprises:

and judging whether the base station ID is matched with the current position base station ID.